-
公开(公告)号：US20210154835A1
公开(公告)日：2021-05-27
申请号：US16734402
申请日：2020-01-05
发明人： HONGJIAN LIU , Zhichao Liu , Jian Zhang , Simin Zhang , Yun Zhao , Youjun Xiong , Jianxin Pang
IPC分类号： B25J9/16
摘要： The present disclosure provides a robot path planning method as well as an apparatus and a robot using the same. The method includes: obtaining a grid map and obtaining a position of obstacle and a position of track in the grid map; determining a cost of grids of the grid map based on the position of obstacle and the position of track; generating a grid cost map based on the cost of the grids and the grid map; and planning a global path of the robot from a current position to a destination position based on the grid cost map. In this manner, it effectively integrates free navigation and track navigation, thereby improving the flexibility of obstacle avoidance and ensuring the safety of obstacle avoidance of the robot.
-
公开(公告)号：US20210056295A1
公开(公告)日：2021-02-25
申请号：US16817554
申请日：2020-03-12
发明人： Jun Cheng , Kui Guo , Jing Gu , Jianxin Pang , Youjun Xiong
摘要： The present disclosure provides a face identification method and a terminal device using the same. The method includes: obtaining a to-be-detected image; performing a brightness enhancement process on the to-be-detected image based on a preset second calculation method to generate a to-be-identified face image; obtaining a first channel value of each channel corresponding to each pixel in the to-be-identified face image; performing another brightness enhancement process on the to-be-identified face image based on each first channel value and a preset first calculation method to obtain a target to-be-identified face image; and performing a face identification process on the target to-be-identified face image to obtain an identification result. Through the above-mentioned scheme, an enhanced face identification manner for the images of low brightness is provided.
-
公开(公告)号：US20200209365A1
公开(公告)日：2020-07-02
申请号：US16396693
申请日：2019-04-28
发明人： Yongsheng Zhao , Youjun Xiong , Zhichao Liu , Jianxin Pang
摘要： The present disclosure provides a laser data calibration method and robot using the same. The method includes: obtaining a pose of a movable device; determining a pose of the lidar based on the pose of the movable device and a transformation relationship between the movable device and the lidar: determining an instantaneous speed of the lidar based on the pose of the lidar at two adjacent time points; determining a delay time of an collection time of one frame of raw laser data obtained through the lidar by scanning for one round with respect to an collection time of a first raw laser data: and obtaining a calibration data of the raw laser data based on the instantaneous speed, tire delay time, and the raw laser data. Through the above-mentioned method, the calibration of the raw laser data can be realized.
-
公开(公告)号：US20200206959A1
公开(公告)日：2020-07-02
申请号：US16709927
申请日：2019-12-11
发明人： Youpeng Li , Youjun Xiong , Hongyu Ding , Meichun Liu , Jianxin Pang
摘要： A robotic arm assembly includes a main body, a number of servos arranged within the main body, each of which has an output shaft, and a rotary connection member connected to the output shaft of one of the servos at a first end of the main body. The rotary connection member defines a through hole allows cables to pass therethrough.
-
公开(公告)号：US20200206935A1
公开(公告)日：2020-07-02
申请号：US16508335
申请日：2019-07-11
发明人： YOUJUN XIONG , Hanyu Sun , Wenhua Fan , Lifu Zhang , Zhongliang Wang , Jianxin Pang
摘要： The present disclosure provides a servo calibration method as well as an apparatus and a robot using the same. The method includes: obtaining data of a position sensor on a motor shaft of the servo; obtaining data of a position sensor on an output shaft of the servo; determining whether a clutch protection has been performed on the servo based on data of the position sensor on the motor shaft and data of the position sensor on the output shaft; and calibrating a position of the motor shaft based on the data of the position sensor on the output shaft, if the clutch protection has been performed on the servo. Through the present disclosure, the problem in the prior art that the process of the calibration is cumbersome can be solved.
-
公开(公告)号：US20200161803A1
公开(公告)日：2020-05-21
申请号：US16445243
申请日：2019-06-19
发明人： Youjun Xiong , Wenhua Fan , Jianxin Pang
摘要： An electronic building block includes a first side and a second side, a first magnet fixed to the first side and including a number of first magnet segments, a second magnet fixed to the second side and including a number of second magnet segments, a first power contact, a second power contact and a first communication contact arranged on the first side; and a third power contact, a fourth power contact and a second communication contact arranged on the second side and respectively coming into contact with the first power contact, the second power contact, and the first communication contact when the first magnet segments of one of two electronic building blocks is connected to the second magnet segments of the other of two electronic building blocks.
-
公开(公告)号：US20240331173A1
公开(公告)日：2024-10-03
申请号：US18603100
申请日：2024-03-12
发明人： BAIYU PAN , Jianxin Pang
CPC分类号： G06T7/50 , G06V10/7715 , G06V10/82 , G06T2207/20228
摘要： A method for binocular depth estimation is provided, including: obtaining binocular images and performing feature extraction on the binocular images to obtain left and right feature mappings; performing disparity construction by using the left and right feature mappings to obtain a disparity cost volume with a reduced dimension; performing attention feature learning on the disparity cost volume to obtain an attention feature vector and performing feature weighting on the disparity cost volume by using the attention feature vector to obtain a weighted cost volume; performing disparity regression on the weighted cost volume based on a two-dimensional convolution to obtain a prediction disparity map; and performing disparity depth conversion on the prediction disparity map to obtain a depth map of the binocular images.
-
公开(公告)号：US11850747B2
公开(公告)日：2023-12-26
申请号：US17112569
申请日：2020-12-04
发明人： Miaochen Guo , Jun Cheng , Jingtao Zhang , Shuping Hu , Dong Wang , Jianxin Pang , Youjun Xiong
CPC分类号： B25J9/161 , B25J9/1697 , B25J19/023 , G06N3/08
摘要： The present disclosure provides an action imitation method as well as a robot and a computer readable storage medium using the same. The method includes: collecting a plurality of action images of a to-be-imitated object; processing the action images through a pre-trained convolutional neural network to obtain a position coordinate set of position coordinates of a plurality of key points of each of the action images; calculating a rotational angle of each of the linkages of the to-be-imitated object based on the position coordinate sets of the action images; and controlling a robot to move according to the rotational angle of each of the linkages of the to-be-imitated object. In the above-mentioned manner, the rotational angle of each linkage of the to-be-imitated object can be obtained by just analyzing and processing the images collected by an ordinary camera without the help of high-precision depth camera.
-
69.发明公开公开(公告)号：US20230386244A1
公开(公告)日：2023-11-30
申请号：US18078027
申请日：2022-12-08
发明人： SHUPING HU , Kan Wang , Huan Tan , Jianxin Pang
IPC分类号： G06V40/10 , G06V10/776 , G06V10/74
CPC分类号： G06V40/103 , G06V10/776 , G06V10/761
摘要： A person re-identification method, a storage medium, and a terminal device are provided. In the method, a preset ratio-based triplet loss function is used as a loss function during training The ratio-based triplet loss function limits a ratio of a positive sample feature distance to a negative sample feature distance to be less than a preset ratio threshold. The positive sample feature distance is a distance between a reference image feature and a positive sample image feature, and the negative sample feature distance is a distance between the reference image feature and a negative sample image feature. Compared with the existing absolute distance-based triplet loss function, in the case of small inter-class differences and large intra-class differences, the ratio-based triplet loss function can effectively improve the stability of model training, the features extracted by the trained model are more discriminative and robust, thereby improving the accuracy of person re-identification results.
-
公开(公告)号：US11693430B2
公开(公告)日：2023-07-04
申请号：US17114526
申请日：2020-12-08
发明人： Jie Bai , Ligang Ge , Yizhang Liu , Hongge Wang , Jianxin Pang , Youjun Xiong
IPC分类号： G05D1/02 , G05D1/08 , B62D57/02 , G05B19/4155
CPC分类号： G05D1/0891 , B62D57/02 , G05B19/4155 , G05D1/0212 , G05B2219/40233
摘要： A computer-implemented gait planning method includes: determining a pitch angle between a foot of the robot and a support surface where the robot stands; determining a support point on a sole of the foot according to the pitch angle; calculating an ankle-foot position vector according to the support point, wherein the ankle-foot position vector is a position vector from an ankle of the robot to a support point on a sole of the foot; calculating a magnitude of change of an ankle position according to the pitch angle and the ankle-foot position vector; and obtaining a compensated ankle position by compensating the ankle position according to the magnitude of change of the ankle position.
-
-
-
-
-
-
-
-
-
搜索结果
120 条记录 (耗时 0.017 秒)
